Return to search results
AFSC/RACE/MACE: 2019-2020 Salmon and Pollock Object Detection
This dataset contains the annotated data, object detection models, and video data used to fine-tune and evaluate object detection models for salmon and pollock detection in videos collected in a commercial pollock trawl in Alaska. The annotated data contains track annotations for all Pacific salmon (Oncorhynchus spp.) and walleye pollock (Gadus chalcogrammus) present and frame level annotations that describe the trawl and background conditions. The annotated data is composed of 11,572 salmon and 73,394 pollock annotations from 16,989 video frames that came from 184 video clips. Five-fold cross validation was used to evaluate EfficientDet D2 and YOLO11n object detection models, and this dataset includes all of these models and a single-class, salmon-only YOLO11n model. In addition to the annotated video frames that are provided as images, videos from three fishing tows that were not annotated are included with their respective YOLO11n detections. These three fishing tows were used to further evaluate the object detection performance of the best performing pollock and salmon model and the salmon-only model.
Resources
3 resources available
-
2019-2020 Salmon and Pollock Object Detection dataset
TEXT/HTML -
GCMD Keyword Forum Page
TEXT/HTML -
Full Metadata Record
TEXT/HTML
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | non-public |
| contactPoint |
{ "fn": "Wilson, Katherine", "@type": "vcard:Contact", "hasEmail": "mailto:katherine.wilson@noaa.gov" } |
| describedByType | application/octet-steam |
| description | This dataset contains the annotated data, object detection models, and video data used to fine-tune and evaluate object detection models for salmon and pollock detection in videos collected in a commercial pollock trawl in Alaska. The annotated data contains track annotations for all Pacific salmon (Oncorhynchus spp.) and walleye pollock (Gadus chalcogrammus) present and frame level annotations that describe the trawl and background conditions. The annotated data is composed of 11,572 salmon and 73,394 pollock annotations from 16,989 video frames that came from 184 video clips. Five-fold cross validation was used to evaluate EfficientDet D2 and YOLO11n object detection models, and this dataset includes all of these models and a single-class, salmon-only YOLO11n model. In addition to the annotated video frames that are provided as images, videos from three fishing tows that were not annotated are included with their respective YOLO11n detections. These three fishing tows were used to further evaluate the object detection performance of the best performing pollock and salmon model and the salmon-only model. |
| distribution |
[ { "@type": "dcat:Distribution", "title": "2019-2020 Salmon and Pollock Object Detection dataset", "accessURL": "https://console.cloud.google.com/storage/browser/nmfs_odp_afsc/RACE/MACE/salmon_pollock_object_detection/", "mediaType": "text/html", "description": "This folder within the Alaska Fisheries Science Center's Google cloud storage contains the data and object detection models used for the Wilson et al. 2025 study on automated salmon and pollock detection in trawl videos from the Alaska commercial pollock fishery. The 'annotated_data' folder contains a folder for each of the 184 video clips used in the study that provides video frames as png files and the annotations as a custom COCO json file. The 'tow_data' folder contains videos as .mov files and csv files of fish detections for three fishing tows that were also used in the study to further evaluate object detection model performance. The 'models' folder contains the object detection models that were used in the study. The 'documentation' folder contains text files that provide details about the data and the cloud storage file structure.", "describedByType": "application/octet-stream" }, { "@type": "dcat:Distribution", "title": "GCMD Keyword Forum Page", "accessURL": "https://forum.earthdata.nasa.gov/app.php/tag/GCMD%2BKeywords", "mediaType": "text/html", "description": "Global Change Master Directory (GCMD). 2026. GCMD Keywords, Version 24. Greenbelt, MD: Earth Science Data and Information System, Earth Science Projects Division, Goddard Space Flight Center (GSFC), National Aeronautics and Space Administration (NASA). URL (GCMD Keyword Forum Page): https://forum.earthdata.nasa.gov/app.php/tag/GCMD+Keywords", "describedByType": "application/octet-stream" }, { "@type": "dcat:Distribution", "title": "Full Metadata Record", "accessURL": "https://www.fisheries.noaa.gov/inport/item/69412", "mediaType": "text/html", "description": "View the complete metadata record on InPort for more information about this dataset.", "describedByType": "application/octet-stream" } ] |
| identifier | https://data.noaa.gov/waf/NOAA/nmfs/afsc/iso/xml/69412.xml |
| issued | 2023-03-08T00:00:00.000+00:00 |
| keyword |
[ "detection", "pollock", "salmon", "tracking", "trawls", "video", "DOC/NOAA/NMFS/AFSC > Alaska Fisheries Science Center, National Marine Fisheries Service, NOAA, U.S. Department of Commerce", "Conservation Engineering Research" ] |
| landingPage | https://www.fisheries.noaa.gov/inport/item/69412 |
| language |
[]
|
| license | https://creativecommons.org/publicdomain/zero/1.0/ |
| modified | 2025-09-25T00:00:00.000+00:00 |
| publisher |
{ "name": "Alaska Fisheries Science Center", "@type": "org:Organization" } |
| rights | otherRestrictions, unclassified |
| spatial | -164.5,54.33333333333,-166.0,55.33333333333 |
| temporal | 2019-06-01T00:00:00+00:00/2019-06-30T00:00:00+00:00 |
| theme |
[ "geospatial" ] |
| title | AFSC/RACE/MACE: 2019-2020 Salmon and Pollock Object Detection |
